Explainability · Aperivue/medsci-skills
Validate Grad-CAM and saliency maps for medical imaging
Checks or helps build the interpretability analysis behind a medical-imaging model, running Adebayo sanity checks, measuring localization against ground truth, and reporting results across a cohort instead of a few chosen examples.
Good for
- Run Adebayo sanity checks on saliency maps
- Score Grad-CAM localization against ground truth
- Write the interpretability section of a paper
- Source repository
- Aperivue/medsci-skills
- Category
- Medicine
Open-source skills are maintained by their authors and listed as published, with attribution. Results depend on how well the skill fits your task and material.
A good place to start
Audit our Grad-CAM heatmaps with Adebayo sanity checks and a cohort-level localization metric.
Make your next great thing.
Bring a question, a file, or an idea that’s not quite there yet.